top | item 47209064

(no title)

ako | 7 hours ago

Biggest downside of CLI for me is that it needs to run in a container. You're allowing the agent to run CLI tools, so you need to limit what it can do.

discuss

order

wolttam|7 hours ago

It gets significantly harder to isolate the authentication details when the model has access to a shell, even in a container. The CLI tool that the model is running may need to access the environment or some credentials file, and what's to stop the model from accessing those credentials directly?

It breaks most assumptions we have about the shell's security model.

tuwtuwtuwtuw|7 hours ago

Couldn't that be solved by whitelisting specific commands?

wolttam|7 hours ago

Such a mechanism would need to be implemented at `execve`, because it would be too easy for the model to stuff the command inside a script or other executable.

g947o|5 hours ago

Give it a try, and challenge yourself (or ChatGPT) to break it.

You'll quickly realize that this is not feasible.